REILX
/

llava-Qwen2-7B-Instruct-Chinese-CLIP

Image-Text-to-Text

txtimage-to-txt

Model card Files Files and versions Community

REILX commited on Jul 10, 2024

Commit

a183c61

·

verified ·

1 Parent(s): 6d6b671

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ tags:
 - lora
 ---
-### 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力，达到gpt4o、claude-3.5-sonnet的识别水平！
 1. 模型结构：</br>
 llava-Qwen2-7B-Instruct-Chinese-CLIP = Qwen/Qwen2-7B-Instruct + multi_modal_projector + OFA-Sys/chinese-clip-vit-large-patch14-336px</br>

 - lora
 ---
+### 模型 llava-Qwen2-7B-Instruct-Chinese-CLIP 增强中文文字识别能力和表情包内涵识别能力，接近gpt4o、claude-3.5-sonnet的识别水平！
 1. 模型结构：</br>
 llava-Qwen2-7B-Instruct-Chinese-CLIP = Qwen/Qwen2-7B-Instruct + multi_modal_projector + OFA-Sys/chinese-clip-vit-large-patch14-336px</br>